Rawlsian fair adaptation of deep learning classifiers

K Shah, P Gupta, A Deshpande… - Proceedings of the 2021 …, 2021 - dl.acm.org
Group-fairness in classification aims for equality of a predictive utility across different
sensitive sub-populations, eg, race or gender. Equality or near-equality constraints in group …
被引用次数：12 相关文章
[PDF] iisc.ac.in

[PDF][PDF] Rawlsian Fair Adaptation of Deep Learning Classifiers

K Shah, P Gupta, A Deshpande, C Bhattacharyya - 2021 - mllab.csa.iisc.ac.in
Algorithmic decisions and risk assessment tools in real-world applications, eg, recruitment,
loan qualification, recidivism, have several examples of effective and scalable black-box …

Rawlsian Fair Adaptation of Deep Learning Classifiers

K Shah, P Gupta, A Deshpande… - arXiv preprint arXiv …, 2021 - arxiv.org
Group-fairness in classification aims for equality of a predictive utility across different
sensitive sub-populations, eg, race or gender. Equality or near-equality constraints in group …

Rawlsian Fair Adaptation of Deep Learning Classifiers

K Shah, P Gupta, A Deshpande… - … 2021-Proceedings of …, 2021 - eprints.iisc.ac.in
Group-fairness in classification aims for equality of a predictive utility across different
sensitive sub-populations, eg, race or gender. Equality or near-equality constraints in group …

Rawlsian Fair Adaptation of Deep Learning Classifiers

K Shah, P Gupta, A Deshpande… - arXiv e …, 2021 - ui.adsabs.harvard.edu
Group-fairness in classification aims for equality of a predictive utility across different
sensitive sub-populations, eg, race or gender. Equality or near-equality constraints in group …

Rawlsian Fair Adaptation of Deep Learning Classifiers

K Shah, P Gupta, A Deshpande, C Bhattacharyya - aies-conference.com
• Characterization of a fair classifier under Pareto efficiency and Rawlsian least-difference
principle• Rawlsian fair adaptation to learn a threshold (on score) or a linear threshold …